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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "particularly" and similar expressions that emphasize specific instances or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akeru
    -0.71
    ilib
    -0.69
    pressed
    -0.69
    only
    -0.67
    Complete
    -0.67
    friend
    -0.65
    readable
    -0.65
    elo
    -0.65
    legates
    -0.65
    uble
    -0.65
    POSITIVE LOGITS
     those
    1.27
     ones
    1.02
    those
    0.93
     pertaining
    0.89
     regarding
    0.88
     through
    0.84
     during
    0.84
     towards
    0.80
     toward
    0.80
     involving
    0.79
    Act Density 0.090%

    No Known Activations