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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to expectations and inevitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orth
    -0.17
    ector
    -0.15
    ]={↵
    -0.14
    .Serial
    -0.14
    umes
    -0.14
    ãĥĢãĥ¼
    -0.14
    wich
    -0.13
    ifier
    -0.13
    ł
    -0.13
    iance
    -0.13
    POSITIVE LOGITS
    isel
    0.16
    ouri
    0.15
    ripsi
    0.15
    ssi
    0.15
    achu
    0.14
    chte
    0.14
    TypeInfo
    0.14
    .openg
    0.13
    965
    0.13
    abwe
    0.13
    Act Density 0.008%

    No Known Activations