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

    Neuronpedia

    INDEX
    Explanations

    particular words indicating emphasis or strong assertion

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tails
    -0.77
    AMS
    -0.70
    HT
    -0.68
    oS
    -0.67
    hm
    -0.67
    hens
    -0.67
    hen
    -0.66
    umat
    -0.66
    guard
    -0.66
    orah
    -0.64
    POSITIVE LOGITS
     they
    0.84
     justifies
    0.76
     unless
    0.73
     anybody
    0.71
     anyone
    0.69
     witches
    0.69
     contradicts
    0.68
     '[
    0.68
     there
    0.68
    milo
    0.67
    Act Density 0.224%

    No Known Activations