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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cradle
    -0.68
    onite
    -0.66
     millisec
    -0.65
     mosqu
    -0.64
    ciating
    -0.63
    ardless
    -0.61
    abase
    -0.60
     ignor
    -0.59
    ileged
    -0.59
    eling
    -0.59
    POSITIVE LOGITS
     ISI
    0.77
     âĨij
    0.73
    âĨij
    0.67
    âĨ
    0.67
     However
    0.67
    sbm
    0.66
     wik
    0.64
    CVE
    0.63
    Appearances
    0.63
    Appearance
    0.63
    Act Density 0.051%

    No Known Activations