Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to emotional or physical interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Third-person pronoun followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    pronoun/name then action/feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.64
    AnchorTagHelper
    -0.63
     @"/
    -0.62
    contentLoaded
    -0.61
    iecie
    -0.60
    CreateModel
    -0.59
    fjspx
    -0.59
    userdetails
    -0.58
    elemField
    -0.58
     AssemblyTitle
    -0.57
    POSITIVE LOGITS
     wondered
    0.66
     felt
    0.64
     wondering
    0.59
     flattered
    0.58
     watched
    0.54
    近平
    0.54
    ResumeLayout
    0.54
     myſelf
    0.54
    Feeling
    0.53
     feel
    0.53
    Act Density 0.123%

    No Known Activations