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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recommendations or evaluations related to performance or returns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thus
    -0.26
     therefore
    -0.25
    thus
    -0.21
    Thus
    -0.18
     Thus
    -0.17
    Therefore
    -0.17
    åĽłæѤ
    -0.17
     поÑįÑĤомÑĥ
    -0.17
     così
    -0.16
     Therefore
    -0.16
    POSITIVE LOGITS
    _oauth
    0.15
     Twin
    0.15
     VECTOR
    0.14
    962
    0.14
    Tcp
    0.14
     Bol
    0.14
    ToF
    0.14
    виÑħ
    0.14
    orative
    0.14
    ncmp
    0.13
    Act Density 0.055%

    No Known Activations