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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate expectations being met or unmet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obo
    -0.15
    lexport
    -0.15
    sei
    -0.14
    pio
    -0.14
    emics
    -0.14
    fare
    -0.14
    resse
    -0.14
    Io
    -0.14
     thr
    -0.14
    hev
    -0.14
    POSITIVE LOGITS
     billing
    0.16
    /epl
    0.15
     measure
    0.15
    icable
    0.15
     Billing
    0.15
    Opaque
    0.14
     living
    0.14
    aze
    0.14
    billing
    0.14
     true
    0.14
    Act Density 0.011%

    No Known Activations