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

    Neuronpedia

    INDEX
    Explanations

    instances where a situation or outcome is described as being influenced by specific factors

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "given" indicating reasoning or conditions in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addle
    -0.74
    ereo
    -0.71
    quin
    -0.69
    ashington
    -0.66
    Bay
    -0.65
    Phoenix
    -0.64
    achel
    -0.63
    acc
    -0.63
    imming
    -0.63
    iami
    -0.62
    POSITIVE LOGITS
    pend
    0.82
     precedence
    0.81
    giving
    0.75
     precedent
    0.73
    aways
    0.70
     away
    0.68
    ¶æ
    0.67
    bidden
    0.67
    away
    0.66
     circumstances
    0.64
    Act Density 0.022%

    No Known Activations