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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or changes related to responsibilities and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikip
    -0.15
    ange
    -0.14
    isper
    -0.14
    perature
    -0.14
    deaux
    -0.14
    Æ°a
    -0.13
    .Condition
    -0.13
    âng
    -0.13
     vý
    -0.13
    izzer
    -0.13
    POSITIVE LOGITS
    starts
    0.15
     sand
    0.15
    IMA
    0.14
    atz
    0.14
    ahlen
    0.14
     auth
    0.14
     Bened
    0.14
    ikler
    0.14
     hypoth
    0.14
     marsh
    0.14
    Act Density 0.009%

    No Known Activations