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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing negative or extreme qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey strong negative sentiments or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    someone
    -0.71
    ecause
    -0.70
    region
    -0.69
    skilled
    -0.69
     oneself
    -0.68
     Logged
    -0.68
    aples
    -0.67
    olean
    -0.65
    needed
    -0.64
    common
    -0.64
    POSITIVE LOGITS
     foray
    1.17
     penchant
    1.11
     inability
    1.06
     insistence
    1.05
    ness
    1.04
     obsession
    1.02
     antics
    1.02
     efforts
    1.01
     stance
    0.99
     refusal
    0.97
    Act Density 0.257%

    No Known Activations