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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obtaining or providing as much information or support as possible

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the need to maximize quantity or quantity-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eri
    -0.71
    ainer
    -0.69
    onomy
    -0.68
    heimer
    -0.68
    UTH
    -0.68
    EStream
    -0.67
    yne
    -0.65
    hler
    -0.65
    cv
    -0.64
    ICA
    -0.64
    POSITIVE LOGITS
     possible
    1.07
     practicable
    0.97
    pects
    0.73
     usual
    0.72
     cheaply
    0.71
     feas
    0.70
    catch
    0.68
     Possible
    0.66
    lihood
    0.65
    perse
    0.64
    Act Density 0.056%

    No Known Activations