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

    Neuronpedia

    INDEX
    Explanations

    specific action verbs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dresden
    -0.65
     dotted
    -0.61
     slashed
    -0.61
    houses
    -0.60
    tch
    -0.59
    ãĤ´ãĥ³
    -0.55
    Apr
    -0.54
    been
    -0.54
    dq
    -0.53
     gal
    -0.53
    POSITIVE LOGITS
     properly
    0.73
    ealous
    0.71
     complicate
    0.69
    irtual
    0.68
    uate
    0.67
    ohyd
    0.66
     nutshell
    0.65
     qualify
    0.64
    oulos
    0.64
     clarification
    0.64
    Act Density 0.122%

    No Known Activations