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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transformations or conversions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and verbs related to conversion or transformation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icho
    -0.67
    andowski
    -0.67
     congr
    -0.67
    aryn
    -0.66
    ARI
    -0.66
    iator
    -0.63
    thank
    -0.62
    spr
    -0.62
    yd
    -0.61
    yy
    -0.61
    POSITIVE LOGITS
     theirs
    0.94
     its
    0.71
     their
    0.70
    pload
    0.69
     hers
    0.66
     whom
    0.66
     healthier
    0.66
     remotely
    0.66
     modem
    0.65
     manageable
    0.64
    Act Density 0.404%

    No Known Activations