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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the purpose or intended outcome of actions

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

    "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    came to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الدراسه
    -0.59
     وتسجيلات
    -0.52
    enseits
    -0.51
    iettivo
    -0.49
    bability
    -0.47
    LJ
    -0.47
     Guin
    -0.47
     tyme
    -0.45
    Hadi
    -0.44
    lette
    -0.43
    POSITIVE LOGITS
    fjspx
    0.85
    IntoConstraints
    0.79
    EndContext
    0.68
    MessageOf
    0.68
     betweenstory
    0.65
    FieldNumber
    0.63
    DockStyle
    0.63
     grips
    0.62
    SharedDtor
    0.62
     kasarigan
    0.61
    Act Density 0.055%

    No Known Activations