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

    Neuronpedia

    INDEX
    Explanations

    references to imminent danger or catastrophic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.71
    cèse
    -0.67
    campista
    -0.65
    henswürdigkeiten
    -0.64
     myſelf
    -0.63
     Autorisations
    -0.63
     esboço
    -0.60
     المعيارى
    -0.60
     AssemblyTitle
    -0.60
    Sucesor
    -0.59
    POSITIVE LOGITS
    #
    0.56
    kreuz
    0.51
     tunn
    0.49
    CRI
    0.48
    秘
    0.48
     ativar
    0.48
     misterioso
    0.47
     seal
    0.46
    はじめに
    0.46
    reactstrap
    0.46
    Act Density 0.465%

    No Known Activations