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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a general or overall situation or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a general sense of participation or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anth
    -0.65
    antha
    -0.64
    jriwal
    -0.63
    Draft
    -0.61
    Chair
    -0.61
     sleeper
    -0.61
     pione
    -0.60
     laure
    -0.59
    rigan
    -0.59
     Collective
    -0.57
    POSITIVE LOGITS
    Downloadha
    0.98
    aking
    0.72
    isan
    0.72
     consists
    0.69
    isans
    0.67
     thereof
    0.66
     (>
    0.65
     resembles
    0.61
    ography
    0.61
     (~
    0.60
    Act Density 0.016%

    No Known Activations