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

    Neuronpedia

    INDEX
    Explanations

    instances of strong opposition or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vert
    -0.17
    Ỽt
    -0.16
    empo
    -0.15
    incible
    -0.15
     ÑģÑĤÑĥд
    -0.15
     Boy
    -0.15
    urnished
    -0.15
    cust
    -0.14
     Balls
    -0.14
    vinc
    -0.14
    POSITIVE LOGITS
    abble
    0.19
     salt
    0.15
     intr
    0.15
    gor
    0.15
     lang
    0.15
     solid
    0.15
    atura
    0.14
    aber
    0.14
     tender
    0.14
     tide
    0.14
    Act Density 0.000%

    No Known Activations