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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional or subjective responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mektedir
    -0.76
    melidir
    -0.59
     которое
    -0.57
    ktop
    -0.56
     rok
    -0.55
    maktadır
    -0.54
    toPromise
    -0.53
     zij
    -0.53
    getResultList
    -0.53
     Rumuni
    -0.52
    POSITIVE LOGITS
     تانيه
    0.82
    '),
    0.77
    InputBorder
    0.75
     outta
    0.71
     purpoſe
    0.70
    "],
    0.69
    ...');
    0.69
    "]]
    0.69
    "),
    0.68
    "");
    0.68
    Act Density 0.275%

    No Known Activations