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

    Neuronpedia

    INDEX
    Explanations

    elements indicating emotional responses and quality assessments in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessness
    -0.23
    raq
    -0.17
    ABILITY
    -0.16
    uation
    -0.16
    formace
    -0.16
    еÑĩение
    -0.15
    _mE
    -0.15
    IBILITY
    -0.15
    ILES
    -0.15
    lator
    -0.15
    POSITIVE LOGITS
     enough
    0.47
    ly
    0.31
    ely
    0.29
     Enough
    0.27
    ised
    0.26
     AF
    0.26
    ized
    0.26
    izable
    0.25
    istic
    0.24
     compared
    0.23
    Act Density 0.707%

    No Known Activations