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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cil
    -0.72
    TA
    -0.70
    nick
    -0.70
    Zip
    -0.70
    hop
    -0.70
     ancest
    -0.68
    ////////////////////////////////
    -0.68
    kered
    -0.65
    eret
    -0.64
     reluct
    -0.63
    POSITIVE LOGITS
     Integrity
    0.81
     Scientology
    0.76
     Investigation
    0.75
     UFOs
    0.75
     Journalism
    0.74
     whether
    0.73
     Probe
    0.71
     Investigations
    0.70
     probing
    0.69
     journalism
    0.67
    Act Density 0.034%

    No Known Activations