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

    Neuronpedia

    INDEX
    Explanations

    adverbs expressing certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    expressions of certainty or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.90
    issy
    -0.78
    ocene
    -0.77
    AME
    -0.76
    orie
    -0.75
    anwhile
    -0.69
    uese
    -0.69
    ricks
    -0.69
    artment
    -0.68
    arro
    -0.67
    POSITIVE LOGITS
     deserved
    0.74
     irritated
    0.70
     satisfied
    0.67
     surely
    0.67
     tempted
    0.67
    footed
    0.67
     "$:/
    0.67
    è¦
    0.66
     annoyed
    0.66
     rejo
    0.65
    Act Density 0.010%

    No Known Activations