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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigations and official inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bench
    -0.15
    chas
    -0.15
     sneak
    -0.15
     çŃ
    -0.15
    VERRIDE
    -0.14
     soaked
    -0.14
    ilon
    -0.14
    uhl
    -0.14
     Inspir
    -0.13
     nackte
    -0.13
    POSITIVE LOGITS
     investigation
    0.52
     investigations
    0.43
     probe
    0.42
    invest
    0.41
     Investigation
    0.40
     investigating
    0.37
     probes
    0.37
     investigate
    0.36
     investig
    0.35
     investigators
    0.35
    Act Density 0.125%

    No Known Activations