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

    Neuronpedia

    INDEX
    Explanations

    instances where something is given or offered to someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of being "given" or "offered" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Austral
    -0.65
    abiding
    -0.61
     Confeder
    -0.60
    aim
    -0.60
    Listener
    -0.59
    MQ
    -0.58
    ASE
    -0.58
    fish
    -0.58
    rouse
    -0.57
    ENT
    -0.57
    POSITIVE LOGITS
    eln
    0.79
    rious
    0.73
     aback
    0.73
     scraps
    0.71
     opportunities
    0.70
     latitude
    0.68
     permission
    0.66
     copies
    0.65
    ĸļ
    0.64
     choice
    0.62
    Act Density 0.087%

    No Known Activations