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

    Neuronpedia

    INDEX
    Explanations

    pairs of names indicating relationships or connections

    oai_token-act-pair · gpt-3.5-turbo

    details about individuals involved in incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     maxim
    -0.73
     handshake
    -0.68
     swall
    -0.67
    Pub
    -0.64
     refreshing
    -0.63
     ballpark
    -0.63
     compromises
    -0.63
     decon
    -0.62
     critiques
    -0.61
     compost
    -0.61
    POSITIVE LOGITS
    ipal
    0.88
    umar
    0.87
     Malik
    0.79
     Mohamed
    0.78
    jamin
    0.78
    nette
    0.77
     Doe
    0.76
    daughter
    0.74
     youngest
    0.74
    ernandez
    0.74
    Act Density 0.288%

    No Known Activations