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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the availability of various options or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tucker
    -0.14
    ieri
    -0.14
    ennes
    -0.13
    .Kind
    -0.13
    Äįel
    -0.13
    utom
    -0.13
    ting
    -0.13
     dö
    -0.13
    oton
    -0.12
     heaven
    -0.12
    POSITIVE LOGITS
     McCart
    0.16
     options
    0.15
     ways
    0.15
    Available
    0.15
    _MS
    0.14
    opcion
    0.14
     Wayback
    0.14
    enso
    0.14
    óc
    0.14
     laure
    0.14
    Act Density 0.100%

    No Known Activations