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

    Neuronpedia

    INDEX
    Explanations

    details related to historical events and personal identities

    oai_token-act-pair · gpt-3.5-turbo

    events and significant figures in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therein
    -0.61
     thereof
    -0.60
     thereto
    -0.58
    .''
    -0.54
     outwe
    -0.53
    .","
    -0.53
    ]."
    -0.53
     domestically
    -0.51
     *.
    -0.50
     predec
    -0.50
    POSITIVE LOGITS
    iannopoulos
    0.66
     Sins
    0.63
     Feminist
    0.62
    ©¶æ
    0.60
     Vegan
    0.58
    tower
    0.58
     Bris
    0.58
    girl
    0.58
    galitarian
    0.57
     Ging
    0.56
    Act Density 2.224%

    No Known Activations