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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating attribution or quoting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "put it" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.74
    riott
    -0.72
    ivic
    -0.68
    è¦ļéĨĴ
    -0.65
    zza
    -0.65
    bie
    -0.63
     Hear
    -0.61
    Legendary
    -0.60
    cue
    -0.60
     Associated
    -0.58
    POSITIVE LOGITS
     forth
    1.32
     together
    1.28
     forward
    1.12
    atively
    0.98
     toget
    0.84
    igated
    0.82
    tered
    0.81
    downs
    0.80
    together
    0.76
     Forth
    0.76
    Act Density 0.057%

    No Known Activations