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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or development

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "along the way"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    encer
    -0.79
    ĸļ
    -0.75
    itton
    -0.71
    ¥µ
    -0.69
    iosyncr
    -0.68
    incinn
    -0.67
    uster
    -0.64
     livest
    -0.64
    igh
    -0.64
     MV
    -0.63
    POSITIVE LOGITS
    steps
    0.87
    ward
    0.80
    fare
    0.75
    point
    0.71
    finding
    0.69
    ulkan
    0.68
    WARD
    0.68
    arity
    0.66
    calling
    0.66
    here
    0.66
    Act Density 0.012%

    No Known Activations