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

    Neuronpedia

    INDEX
    Explanations

    terms related to toxic substances, especially poison

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    noon
    -0.94
    astical
    -0.93
    med
    -0.93
    astically
    -0.92
    dar
    -0.90
    ulative
    -0.89
    blance
    -0.88
    atically
    -0.85
    aiden
    -0.81
    uled
    -0.81
    POSITIVE LOGITS
    nect
    1.36
    ition
    1.20
    ously
    1.15
    essee
    1.09
     Ivy
    1.08
    ette
    1.08
    ews
    1.07
    ous
    1.01
     Wonderland
    0.91
     iv
    0.90
    Act Density 0.736%

    No Known Activations