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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with "From"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "From" indicating source references or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.77
    ifix
    -0.76
    stakes
    -0.74
    SPONSORED
    -0.74
    priority
    -0.72
    certain
    -0.71
    seek
    -0.71
    condition
    -0.69
    abouts
    -0.69
    raised
    -0.68
    POSITIVE LOGITS
     afar
    1.09
     whence
    1.04
     Wow
    0.86
     thence
    0.79
     Above
    0.79
     inception
    0.72
     Across
    0.71
     abroad
    0.66
     Below
    0.66
     inside
    0.65
    Act Density 0.042%

    No Known Activations