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

    Neuronpedia

    INDEX
    Explanations

    words related to restrictions or limitations

    oai_token-act-pair · gpt-3.5-turbo

    words associated with restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uka
    -0.67
    anches
    -0.61
    ears
    -0.59
    prints
    -0.59
    ICAN
    -0.58
    akable
    -0.58
    ç«
    -0.57
    Bet
    -0.56
    SU
    -0.56
    furt
    -0.56
    POSITIVE LOGITS
     geographically
    1.00
     solely
    0.93
     thereto
    0.92
     to
    0.88
     by
    0.84
     athlet
    0.77
     unto
    0.76
     strictly
    0.72
     territ
    0.72
     principally
    0.69
    Act Density 0.047%

    No Known Activations