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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here"

    oai_token-act-pair · gpt-3.5-turbo

    the word "here" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.88
    sac
    -0.68
    oppable
    -0.64
     meticulous
    -0.61
     san
    -0.61
     abort
    -0.60
     complete
    -0.60
     imminent
    -0.59
     purchase
    -0.57
     medical
    -0.57
    POSITIVE LOGITS
    here
    1.37
    abouts
    0.95
    terday
    0.90
    iton
    0.89
    upon
    0.82
    nces
    0.79
    tics
    0.79
    theless
    0.79
    landish
    0.78
    bley
    0.78
    Act Density 0.003%

    No Known Activations