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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is inappropriate or not in the expected or proper condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating things that are out of proportion or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rower
    -0.80
    swick
    -0.68
    IDA
    -0.65
    enaries
    -0.65
    erity
    -0.64
    ISA
    -0.64
    ilers
    -0.63
    FORE
    -0.63
    osures
    -0.63
    cause
    -0.62
    POSITIVE LOGITS
    erous
    0.94
     par
    0.81
    whelming
    0.76
    vable
    0.75
     kil
    0.69
     grasp
    0.69
     priorities
    0.68
    humane
    0.67
     fundament
    0.65
    arthy
    0.65
    Act Density 0.123%

    No Known Activations