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

    Neuronpedia

    INDEX
    Explanations

    phrases related to invitations or offers of participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     going
    -0.19
    rit
    -0.15
     heading
    -0.15
    861
    -0.15
     Going
    -0.14
    going
    -0.14
    ami
    -0.14
    aze
    -0.14
    ay
    -0.14
    rh
    -0.14
    POSITIVE LOGITS
     into
    0.42
     onto
    0.36
    into
    0.35
     Into
    0.33
    Into
    0.29
     INTO
    0.29
    onto
    0.27
     vÃło
    0.26
    _into
    0.26
    .into
    0.23
    Act Density 0.061%

    No Known Activations