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

    Neuronpedia

    INDEX
    Explanations

    words related to superlatives or extremes

    oai_token-act-pair · gpt-3.5-turbo

    the word "most" used to signify the majority in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vest
    -0.72
    pload
    -0.68
    icer
    -0.67
     Mellon
    -0.67
    rompt
    -0.66
    instead
    -0.65
    abad
    -0.65
    pton
    -0.61
    nton
    -0.61
    thur
    -0.60
    POSITIVE LOGITS
     importantly
    1.25
    afa
    0.90
    body
    0.90
     notably
    0.89
    tenance
    0.81
    likely
    0.80
    rar
    0.79
     observers
    0.77
     important
    0.76
     likely
    0.74
    Act Density 0.053%

    No Known Activations