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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relationships, origins, or connections in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĦ·
    -0.13
     Pearce
    -0.13
     Promise
    -0.13
     lob
    -0.13
    ayload
    -0.13
    emouth
    -0.12
    Unmarshaller
    -0.12
    owner
    -0.12
    ToProps
    -0.12
    forgettable
    -0.12
    POSITIVE LOGITS
    egas
    0.15
    aves
    0.15
    dra
    0.15
    ecome
    0.15
    ONGL
    0.15
    /of
    0.14
    angelog
    0.14
     nutshell
    0.14
    eps
    0.14
    pha
    0.14
    Act Density 0.218%

    No Known Activations