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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to offering, confirming, signaling, shaping, and informing

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate positive or significant impacts or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encount
    -0.74
     destro
    -0.74
     tyr
    -0.71
    isal
    -0.64
     COURT
    -0.64
    FTWARE
    -0.62
     afore
    -0.61
    issance
    -0.60
     reluct
    -0.60
    witch
    -0.60
    POSITIVE LOGITS
    ings
    1.01
    ingly
    0.93
    geries
    0.79
    ments
    0.78
    ²¾
    0.76
    fully
    0.73
    glers
    0.70
    eth
    0.70
    iors
    0.69
    umbnails
    0.68
    Act Density 0.427%

    No Known Activations