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

    Neuronpedia

    INDEX
    Explanations

    concepts related to individual trajectories and decision-making paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _ctxt
    -0.15
    ìļķ
    -0.14
    ahat
    -0.14
    iji
    -0.14
    leck
    -0.13
    947
    -0.13
    onta
    -0.13
    itler
    -0.13
    ieten
    -0.13
    опиÑģ
    -0.13
    POSITIVE LOGITS
     follow
    0.93
     Follow
    0.89
    follow
    0.87
    Follow
    0.83
     follows
    0.83
    -follow
    0.77
     FOLLOW
    0.77
     followed
    0.74
    _follow
    0.72
    .follow
    0.68
    Act Density 0.192%

    No Known Activations