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

    Neuronpedia

    INDEX
    Explanations

    the word "tit" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    the word "tit" and its variations, as well as phrases related to titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulton
    -0.71
    OURCE
    -0.71
     Conduct
    -0.69
    PRES
    -0.68
    FORMATION
    -0.67
    gur
    -0.67
    âĸ¬
    -0.65
    Downloadha
    -0.65
    ITNESS
    -0.65
     Democracy
    -0.64
    POSITIVE LOGITS
     tit
    0.92
    anic
    0.88
    aunts
    0.87
    gey
    0.84
    hered
    0.82
    acious
    0.82
    ular
    0.81
    araoh
    0.79
    rice
    0.79
    tle
    0.78
    Act Density 0.006%

    No Known Activations