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

    Neuronpedia

    INDEX
    Explanations

    references to detectives and police officers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.93
    eworld
    -0.88
    oÄŁ
    -0.85
    bows
    -0.79
    xual
    -0.75
    yip
    -0.73
    ð
    -0.71
    suff
    -0.71
     deaf
    -0.71
    baby
    -0.71
    POSITIVE LOGITS
     Grimoire
    1.19
     detective
    0.93
     investigator
    0.91
     investigating
    0.90
    ective
    0.90
     Inspector
    0.86
     detectives
    0.86
     Detective
    0.84
     probing
    0.83
     Agency
    0.81
    Act Density 0.044%

    No Known Activations