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

    Neuronpedia

    INDEX
    Explanations

    references to negative emotions and foreboding threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffa
    -0.15
    ahren
    -0.15
    ollen
    -0.15
    onz
    -0.15
    arcy
    -0.14
    iben
    -0.14
    pillar
    -0.14
    ulls
    -0.13
    lobs
    -0.13
    peria
    -0.13
    POSITIVE LOGITS
    OfString
    0.15
    Feel
    0.15
     radiation
    0.15
    jon
    0.15
    าà¸Ħม
    0.14
    inton
    0.14
     vibes
    0.14
    tn
    0.14
    CHA
    0.14
     atmosphere
    0.14
    Act Density 0.132%

    No Known Activations