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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating an aspiration or expectation of a certain status or behavior

    oai_token-act-pair · gpt-3.5-turbo

    expressions of expectation and potential regarding personal goals or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fuk
    -0.62
     IOC
    -0.59
    abal
    -0.59
     Greenpeace
    -0.58
     Gul
    -0.58
     Diesel
    -0.57
     briefs
    -0.57
     Nanto
    -0.57
     Miko
    -0.56
     charcoal
    -0.56
    POSITIVE LOGITS
    !.
    0.96
    .—
    0.85
    .'
    0.84
    .(
    0.80
    .:
    0.80
    .?
    0.80
    .[
    0.80
    .,
    0.80
    .
    0.79
    .</
    0.79
    Act Density 0.260%

    No Known Activations