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

    Neuronpedia

    INDEX
    Explanations

    statements of admission or acknowledgment of past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dra
    -0.73
     Thomas
    -0.66
    :+:
    -0.65
    Dra
    -0.64
    XmlType
    -0.64
    ený
    -0.63
    overrightarrow
    -0.61
     dra
    -0.61
    ClientSize
    -0.61
    Continu
    -0.61
    POSITIVE LOGITS
     admit
    1.38
     Admit
    1.36
     admitted
    1.31
     admits
    1.30
     admitting
    1.27
     Admissions
    1.25
     admissions
    1.23
     confesses
    1.23
    Admissions
    1.16
     confess
    1.16
    Act Density 0.131%

    No Known Activations