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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating source or attribution in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.15
    iming
    -0.15
    visa
    -0.14
    essler
    -0.13
    orch
    -0.13
    ximo
    -0.13
     considerable
    -0.12
    Interop
    -0.12
    whatever
    -0.12
    grily
    -0.12
    POSITIVE LOGITS
    /of
    0.25
    :
    0.18
    ctype
    0.17
    :]
    0.16
    /by
    0.15
    :|
    0.15
    ιÏĩ
    0.15
    ा:
    0.14
    /from
    0.14
    stood
    0.14
    Act Density 0.384%

    No Known Activations