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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal thoughts or reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disbelief or astonishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.74
     Grimm
    -0.68
    rongh
    -0.65
    ghan
    -0.65
    aez
    -0.61
     inform
    -0.59
    Adams
    -0.59
     Underground
    -0.56
     stun
    -0.56
    etheus
    -0.56
    POSITIVE LOGITS
     anymore
    1.02
    enance
    0.84
    ħĭ
    0.75
     âĶľ
    0.72
    âķ
    0.72
    ĵĺ
    0.71
     coincidence
    0.70
     nor
    0.69
     myself
    0.69
    enough
    0.68
    Act Density 0.115%

    No Known Activations