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

    Neuronpedia

    INDEX
    Explanations

    terms related to self-reference and introspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.93
     Bartolo
    -0.66
    шеб
    -0.65
     thanh
    -0.63
    riwal
    -0.60
     rima
    -0.60
     myſelf
    -0.60
     defire
    -0.58
    endaftar
    -0.58
     Heal
    -0.58
    POSITIVE LOGITS
     consideration
    1.45
     Consideration
    1.37
    consider
    1.32
     consider
    1.27
    Consider
    1.25
     CONSIDER
    1.21
     considered
    1.21
    CONSIDER
    1.18
    considered
    1.16
     considers
    1.16
    Act Density 0.164%

    No Known Activations