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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bably
    -0.73
    fits
    -0.71
    pmwiki
    -0.71
    ursed
    -0.69
     reconciliation
    -0.64
     belts
    -0.60
    ests
    -0.60
     autonomy
    -0.59
    ensive
    -0.59
     bearings
    -0.59
    POSITIVE LOGITS
    opher
    1.00
    erver
    0.81
    hire
    0.81
    chant
    0.80
    rina
    0.79
    hou
    0.78
     Christie
    0.77
     Jericho
    0.75
    ophers
    0.75
     Columbus
    0.74
    Act Density 0.879%

    No Known Activations