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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attraction or drawing interest

    oai_token-act-pair · gpt-3.5-turbo

    the word "attracted" and its various uses in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hal
    -0.71
    dam
    -0.66
    minus
    -0.64
    ãĥ¯ãĥ³
    -0.63
    HE
    -0.61
    FT
    -0.60
    ocker
    -0.60
     bunker
    -0.60
    unker
    -0.60
    eden
    -0.59
    POSITIVE LOGITS
     attracted
    1.30
     attracts
    1.10
     attract
    0.96
    xual
    0.91
    dinand
    0.88
     aroused
    0.86
     attracting
    0.86
    GGGGGGGG
    0.83
    entious
    0.82
    ĸļ
    0.80
    Act Density 0.009%

    No Known Activations