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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    иÑĢ
    -0.15
    cba
    -0.14
    ĸ
    -0.14
    /wiki
    -0.13
    (Optional
    -0.13
    uitar
    -0.13
    oris
    -0.13
    .struct
    -0.13
    efa
    -0.13
    umably
    -0.13
    POSITIVE LOGITS
     strongly
    0.28
     compelled
    0.28
     like
    0.24
     duty
    0.23
     comfortable
    0.22
     obliged
    0.21
     Duty
    0.20
     nhÆ°
    0.19
     obligated
    0.19
    Like
    0.19
    Act Density 0.025%

    No Known Activations