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

    Neuronpedia

    INDEX
    Explanations

    situations where something is deemed highly improbable or difficult

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or doubt about outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raint
    -0.83
    lins
    -0.81
    elson
    -0.75
    iya
    -0.75
    waters
    -0.72
    lan
    -0.69
    iak
    -0.68
    io
    -0.68
    lin
    -0.67
    sw
    -0.67
    POSITIVE LOGITS
     forgiven
    0.88
    querque
    0.79
     misunder
    0.79
     qualify
    0.76
     swayed
    0.71
     entertained
    0.71
     exagger
    0.70
     penetrate
    0.70
     infer
    0.69
     quir
    0.68
    Act Density 0.024%

    No Known Activations