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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.80
     ddelweddau
    -0.77
    expandindo
    -0.72
    protoc
    -0.70
    parsedMessage
    -0.70
    bewerken
    -0.69
    xase
    -0.67
     @"/
    -0.66
    esercito
    -0.64
    Personensuche
    -0.63
    POSITIVE LOGITS
     you
    0.69
     it
    0.64
     they
    0.62
     there
    0.58
     we
    0.55
     nobody
    0.51
    icoot
    0.48
     let
    0.47
     give
    0.47
    itone
    0.46
    Act Density 0.224%

    No Known Activations