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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in news or entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceptor
    -0.82
    conservancy
    -0.73
    req
    -0.72
    Ŀ
    -0.72
    opal
    -0.70
    nesota
    -0.68
    respond
    -0.67
    science
    -0.67
    acting
    -0.66
    cephal
    -0.66
    POSITIVE LOGITS
     Lambert
    1.19
     Lerner
    0.90
    oyd
    0.71
    igue
    0.70
    ucci
    0.68
    enstein
    0.68
    ichick
    0.67
    rikes
    0.66
     Dull
    0.66
     DRAG
    0.66
    Act Density 0.013%

    No Known Activations