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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the degree or intensity of a particular condition or situation

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe various conditions or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apego
    -0.87
    encer
    -0.73
    ICAN
    -0.69
    ndra
    -0.69
    endant
    -0.69
    uana
    -0.68
    winner
    -0.67
    APTER
    -0.67
    ourge
    -0.67
    orem
    -0.66
    POSITIVE LOGITS
     increments
    1.16
     circles
    1.04
     situations
    1.01
     manner
    1.00
     contexts
    1.00
     fashion
    0.94
     proportions
    0.91
     guise
    0.91
     places
    0.91
     settings
    0.90
    Act Density 0.238%

    No Known Activations