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

    Neuronpedia

    INDEX
    Explanations

    terms related to detectives and detective work

    oai_token-act-pair · gpt-3.5-turbo

    mentions of detectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eworld
    -0.87
    xual
    -0.86
    bows
    -0.85
    edom
    -0.76
    jri
    -0.76
    ankind
    -0.75
     deaf
    -0.74
    rights
    -0.74
    ularity
    -0.74
    )=(
    -0.72
    POSITIVE LOGITS
     Grimoire
    0.99
     detective
    0.97
     Detective
    0.95
    ective
    0.93
     Inspector
    0.83
     detectives
    0.83
     Detect
    0.82
     Constable
    0.79
     sergeant
    0.75
     Sergeant
    0.71
    Act Density 0.041%

    No Known Activations