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

    Neuronpedia

    INDEX
    Explanations

    negative descriptive adjectives

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing various qualities and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appropriately
    -0.85
    Reloaded
    -0.81
    ModLoader
    -0.72
     Kinn
    -0.68
    efully
    -0.67
    imately
    -0.67
    Effective
    -0.66
    fully
    -0.66
    ably
    -0.65
    ependent
    -0.65
    POSITIVE LOGITS
    ness
    1.26
    ities
    0.99
    hander
    0.93
    tions
    0.86
    ity
    0.84
    iary
    0.83
    nesses
    0.82
    ties
    0.80
    NESS
    0.79
    tion
    0.78
    Act Density 0.408%

    No Known Activations