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

    Neuronpedia

    INDEX
    Explanations

    specific citations or references in formal writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fault
    -0.21
    <fieldset
    -0.19
     fare
    -0.18
    fatal
    -0.18
     fares
    -0.17
    fieldset
    -0.17
    firm
    -0.16
    fare
    -0.16
     fiscal
    -0.16
    fade
    -0.16
    POSITIVE LOGITS
     SF
    0.36
     FF
    0.33
     PF
    0.32
     TF
    0.32
     AF
    0.31
     HF
    0.31
     MF
    0.30
     VF
    0.30
     EF
    0.30
     DF
    0.30
    Act Density 0.256%

    No Known Activations