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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Croatian
    -0.65
     Galileo
    -0.61
     AAC
    -0.61
     srfAttach
    -0.58
     displacement
    -0.56
     karma
    -0.55
     compress
    -0.55
     Ramadan
    -0.54
     Hungarian
    -0.54
     Celsius
    -0.54
    POSITIVE LOGITS
    endon
    0.88
    agall
    0.86
    vey
    0.85
    intosh
    0.82
    wen
    0.79
    adows
    0.79
    ath
    0.78
    ethy
    0.77
    agh
    0.77
    aney
    0.77
    Act Density 0.026%

    No Known Activations