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

    Neuronpedia

    INDEX
    Explanations

    words related to freezing or things becoming frozen

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Frozen" and associated terms related to freezing effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lder
    -0.78
    inct
    -0.66
    ependence
    -0.65
     Hew
    -0.63
    Che
    -0.62
    Carter
    -0.61
    ENCE
    -0.60
     Keynes
    -0.60
    EE
    -0.58
    Anderson
    -0.57
    POSITIVE LOGITS
    uled
    0.98
    ules
    0.89
    steen
    0.83
    vati
    0.83
    inki
    0.82
    gaard
    0.81
    rozen
    0.80
    xual
    0.80
    umenthal
    0.79
    zing
    0.79
    Act Density 0.013%

    No Known Activations