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

    Neuronpedia

    INDEX
    Explanations

    references to theatrical or performance contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amient
    -0.08
    556
    -0.07
    ness
    -0.07
    NESS
    -0.07
    .Alignment
    -0.07
    bakan
    -0.07
    ambi
    -0.07
    lope
    -0.07
    GenerationStrategy
    -0.07
    AMPL
    -0.07
    POSITIVE LOGITS
     presence
    0.12
    Presence
    0.12
     Presence
    0.10
    presence
    0.10
     persona
    0.10
    persona
    0.08
     Persona
    0.08
    yb
    0.07
     personality
    0.07
     personas
    0.06
    Act Density 0.007%

    No Known Activations