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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.50
    ureusement
    -0.49
    ArgsConstructor
    -0.45
    pleft
    -0.45
    saraba
    -0.43
     lenker
    -0.41
    ilets
    -0.41
    hoeddwyd
    -0.40
     antaranya
    -0.40
     همچنین
    -0.39
    POSITIVE LOGITS
    越来越
    0.44
     ever
    0.43
    ReusableCell
    0.42
    always
    0.41
     always
    0.41
    毎回
    0.40
     coraz
    0.40
    越來越
    0.39
     Always
    0.39
    Always
    0.39
    Act Density 0.093%

    No Known Activations