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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating a hypothetical situation

    oai_token-act-pair · gpt-3.5-turbo

    negations or instances of conditions that didn't occur

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \\\\\\\\
    -0.74
    Topic
    -0.73
    IUM
    -0.71
    Values
    -0.71
    unless
    -0.68
    oice
    -0.68
    fter
    -0.68
    ãĤ¦ãĤ¹
    -0.67
    onic
    -0.67
    ãĤµ
    -0.67
    POSITIVE LOGITS
     already
    0.92
     intervened
    0.87
    hin
    0.84
     exist
    0.77
     vetoed
    0.75
     Already
    0.73
     existed
    0.72
     hijacked
    0.70
     jammed
    0.67
     raining
    0.66
    Act Density 0.071%

    No Known Activations