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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to strength

    oai_token-act-pair · gpt-3.5-turbo

    references to strong personalities, characteristics, and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.82
    inea
    -0.79
    etus
    -0.78
     guiActiveUn
    -0.75
    ocaust
    -0.69
    adelphia
    -0.67
     Wonderland
    -0.66
     Duchess
    -0.66
    ा
    -0.66
     botched
    -0.65
    POSITIVE LOGITS
    ngth
    0.73
    tein
    0.73
     defenses
    0.72
     (>
    0.69
     withstand
    0.69
     directional
    0.67
    arming
    0.65
     resists
    0.65
    ghai
    0.65
    ãĤ¤ãĥĪ
    0.64
    Act Density 0.315%

    No Known Activations