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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or decisions being made or implemented

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "put."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.81
    riott
    -0.61
     Veter
    -0.59
     Hear
    -0.57
     forgive
    -0.56
    zza
    -0.56
     Photographer
    -0.56
     rematch
    -0.55
     Suppose
    -0.55
     Delete
    -0.54
    POSITIVE LOGITS
     forth
    1.16
    atively
    1.05
     forward
    0.98
     together
    0.85
    tered
    0.80
    rid
    0.79
     Forth
    0.74
    igated
    0.74
     emphasis
    0.72
    lished
    0.71
    Act Density 0.093%

    No Known Activations