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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing limitations or control over circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icus
    -0.16
    598
    -0.16
    ventus
    -0.15
    rdf
    -0.15
    /Common
    -0.14
    agara
    -0.14
     Cata
    -0.14
    .gdx
    -0.13
    acus
    -0.13
    .jdesktop
    -0.13
    POSITIVE LOGITS
     control
    1.07
    control
    0.95
    -control
    0.92
     Control
    0.90
    Control
    0.83
    _control
    0.82
     CONTROL
    0.81
     controle
    0.79
    æݧåĪ¶
    0.79
     controls
    0.76
    Act Density 0.253%

    No Known Activations