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

    Neuronpedia

    INDEX
    Explanations

    phrases implying speculation or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anchester
    -0.68
    opens
    -0.65
     Rapids
    -0.63
    sterdam
    -0.63
    opened
    -0.61
    Reviewed
    -0.61
    mentation
    -0.60
     survives
    -0.59
     runtime
    -0.59
    archives
    -0.57
    POSITIVE LOGITS
    othy
    0.80
     perform
    0.73
    ggles
    0.70
    urai
    0.70
    anian
    0.69
    icho
    0.69
     indicate
    0.69
     accommodate
    0.68
     be
    0.68
     resemble
    0.68
    Act Density 0.052%

    No Known Activations