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

    Neuronpedia

    INDEX
    Explanations

    mentions of emotional states and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verity
    -0.17
    alar
    -0.16
    abile
    -0.15
    AtPath
    -0.15
    utsch
    -0.15
    egrity
    -0.14
    PCA
    -0.14
    annon
    -0.14
    utton
    -0.14
    ersistence
    -0.14
    POSITIVE LOGITS
     view
    0.17
     believes
    0.16
     opinion
    0.16
     toler
    0.16
     belief
    0.16
     believe
    0.16
    ipi
    0.15
     believed
    0.15
    opper
    0.15
    mant
    0.14
    Act Density 0.341%

    No Known Activations