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

    Neuronpedia

    INDEX
    Explanations

    expressions of possibility or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untime
    -0.17
    ainment
    -0.15
    vice
    -0.14
    shaw
    -0.14
    омеÑĢ
    -0.14
     Uncategorized
    -0.14
    ailer
    -0.14
    ultz
    -0.14
    áºł
    -0.14
    اء
    -0.13
    POSITIVE LOGITS
     be
    0.38
    hem
    0.32
     well
    0.31
    onna
    0.30
    hap
    0.26
    haps
    0.24
    oral
    0.23
    ors
    0.23
     indeed
    0.23
    /m
    0.22
    Act Density 0.077%

    No Known Activations