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

    Neuronpedia

    INDEX
    Explanations

    visual cues and expressions of attention or interaction between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -0.97
    TagMode
    -0.88
    Tikang
    -0.76
     @"/
    -0.72
    évaluateur
    -0.69
     שוליים
    -0.69
    parsedMessage
    -0.68
     Normdatei
    -0.68
     виправивши
    -0.68
    ustimmung
    -0.67
    POSITIVE LOGITS
     blank
    0.52
     jdbcTemplate
    0.42
    amo
    0.42
     waiting
    0.41
     empty
    0.40
    Blank
    0.39
     kvar
    0.39
    手里的
    0.38
     intently
    0.38
     sky
    0.37
    Act Density 0.064%

    No Known Activations