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

    Neuronpedia

    INDEX
    Explanations

    words related to a specialized situation or concept

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãħĭ
    -0.81
     crumbling
    -0.77
     blot
    -0.70
    ulp
    -0.69
     terr
    -0.69
    å°Ĩ
    -0.66
    ournal
    -0.65
    iating
    -0.65
     Fired
    -0.65
     Jamaica
    -0.63
    POSITIVE LOGITS
    bre
    1.29
    itbart
    1.14
    vity
    1.08
    akers
    1.00
    lla
    0.96
    aker
    0.93
    acher
    0.92
    tto
    0.92
    thren
    0.90
    aches
    0.89
    Act Density 0.005%

    No Known Activations