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

    Neuronpedia

    INDEX
    Explanations

    words related to technological development and experimentation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    shock
    -0.76
    gee
    -0.72
    perty
    -0.69
    chy
    -0.63
     Haram
    -0.63
    clad
    -0.62
    pox
    -0.62
    pton
    -0.61
    pload
    -0.60
    BOX
    -0.60
    POSITIVE LOGITS
    ruct
    1.22
    ream
    1.22
    reet
    1.18
    rophe
    1.16
    ophe
    1.16
    ensibly
    1.16
    rict
    1.13
    rike
    1.11
    opher
    1.08
    orian
    1.03
    Act Density 0.883%

    No Known Activations