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

    Neuronpedia

    INDEX
    Explanations

    references to weapons and physical violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.40
     glan
    -1.01
    Autoritní
    -0.92
     realis
    -0.90
     reger
    -0.89
     gie
    -0.85
     stoff
    -0.84
     anse
    -0.84
     kram
    -0.82
     hek
    -0.82
    POSITIVE LOGITS
     impractica
    0.94
     disreg
    0.93
     liberality
    0.91
     ecru
    0.90
     clayey
    0.89
     felicity
    0.89
     friable
    0.85
     earnestness
    0.84
     pymysql
    0.82
     paradiso
    0.81
    Act Density 0.350%

    No Known Activations