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

    Neuronpedia

    INDEX
    Explanations

    words related to collaboration and cooperation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collaboration and cooperation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    waves
    -0.77
     GUN
    -0.65
     Mahjong
    -0.63
     thinly
    -0.63
     biological
    -0.61
     Cth
    -0.60
     marsh
    -0.59
     Widow
    -0.59
     DEL
    -0.59
     writ
    -0.58
    POSITIVE LOGITS
    atives
    2.27
    ators
    2.27
    ative
    2.22
    atively
    2.18
    ating
    1.97
    ator
    1.94
    ated
    1.82
    atorial
    1.76
    ate
    1.70
    ates
    1.69
    Act Density 0.064%

    No Known Activations