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

    Neuronpedia

    INDEX
    Explanations

    chemistry-related terms, specifically focusing on toxicity and numerical or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Conley
    -0.72
     useRef
    -0.71
    utas
    -0.67
     calendriers
    -0.65
    Vidite
    -0.61
    꾼
    -0.61
    cheid
    -0.60
     Maier
    -0.59
    opis
    -0.56
    ué
    -0.54
    POSITIVE LOGITS
    toxicity
    1.44
     تانيه
    0.92
    ſelf
    0.89
    存于互联网档案馆
    0.89
     Koran
    0.86
     muualla
    0.79
    neſs
    0.79
     Houſe
    0.78
    ſelves
    0.76
     InputDecoration
    0.75
    Act Density 0.038%

    No Known Activations