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

    Neuronpedia

    INDEX
    Explanations

    evaluative adjectives and descriptors conveying beauty and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antity
    -0.17
    éĻ°
    -0.17
    .Startup
    -0.15
    ména
    -0.15
    jÃŃ
    -0.15
    taire
    -0.14
    "go
    -0.14
    ruise
    -0.14
    ocene
    -0.14
    .registry
    -0.14
    POSITIVE LOGITS
     sed
    0.50
     capt
    0.46
     hook
    0.41
     ent
    0.40
     Sed
    0.40
     fasc
    0.37
     Hook
    0.36
    sed
    0.35
     magnet
    0.35
    hook
    0.35
    Act Density 0.274%

    No Known Activations