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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "I" and expressions of personal opinion or experience

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

    I believe, am, think, know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.66
    UrlResolution
    -0.54
    IndentedString
    -0.53
    ⟬
    -0.53
    afficheront
    -0.51
    StoryboardSegue
    -0.50
    bootstrapcdn
    -0.50
    DockStyle
    -0.49
    RTEX
    -0.49
    原始内容存档于
    -0.48
    POSITIVE LOGITS
     Mahan
    0.44
     I
    0.42
    Margin
    0.39
     Ramon
    0.39
     suggest
    0.38
     Charles
    0.37
     Ramón
    0.36
    I
    0.36
    conse
    0.36
    sez
    0.35
    Act Density 0.039%

    No Known Activations