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

    Neuronpedia

    INDEX
    Explanations

    possessive forms and references to relationships between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kens
    -0.15
    ico
    -0.14
    ç§
    -0.13
    /self
    -0.13
     coercion
    -0.13
     Slo
    -0.13
    223
    -0.13
     charisma
    -0.13
    inely
    -0.13
    317
    -0.13
    POSITIVE LOGITS
     ability
    0.25
     status
    0.22
     lack
    0.21
     role
    0.20
     position
    0.20
     inability
    0.19
     willingness
    0.18
     abilities
    0.18
     connection
    0.18
     presence
    0.17
    Act Density 0.241%

    No Known Activations