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

    Neuronpedia

    INDEX
    Explanations

    words related to different abilities or capabilities, particularly focusing on technical skills or traits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Surv
    -0.71
     1942
    -0.67
    algia
    -0.67
    gone
    -0.65
     1895
    -0.65
    backer
    -0.64
     Bride
    -0.64
     1943
    -0.63
     1941
    -0.63
    arer
    -0.63
    POSITIVE LOGITS
    Reviewer
    0.95
    ibility
    0.85
    bodied
    0.83
    ibilities
    0.80
    Ability
    0.79
    reys
    0.75
    ually
    0.73
    fully
    0.73
    auga
    0.73
    assisted
    0.71
    Act Density 0.032%

    No Known Activations