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

    Neuronpedia

    INDEX
    Explanations

    invitations or prompts for interaction or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that encourage open communication and sharing of thoughts or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oded
    -0.60
    Lock
    -0.59
    inav
    -0.58
     Locked
    -0.58
     decay
    -0.58
    roph
    -0.58
    onet
    -0.58
     effected
    -0.57
     Sop
    -0.56
    heed
    -0.54
    POSITIVE LOGITS
    zing
    0.81
    istical
    0.66
    zin
    0.65
    cgi
    0.64
     Janeiro
    0.63
    .............
    0.63
     Downloads
    0.63
    zes
    0.63
     volunteering
    0.62
    nee
    0.62
    Act Density 0.029%

    No Known Activations