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

    Neuronpedia

    INDEX
    Explanations

    names of people and places in sentences involving meetings or interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of meetings or conversations involving key individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prev
    -0.69
    Pg
    -0.68
     Purg
    -0.67
     penal
    -0.67
     nutshell
    -0.63
     endif
    -0.61
     depended
    -0.60
     replaced
    -0.58
     ILCS
    -0.58
    Frames
    -0.58
    POSITIVE LOGITS
     representatives
    0.76
    arov
    0.72
    umbn
    0.72
    assadors
    0.72
    omever
    0.71
    armac
    0.70
     whom
    0.70
     advisors
    0.70
    ournal
    0.69
    pport
    0.66
    Act Density 0.735%

    No Known Activations