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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fear and anxiety about self-disclosure or personal secrets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     æŀ
    -0.16
    reamble
    -0.15
    ream
    -0.14
    IGHL
    -0.13
    igu
    -0.13
     Southern
    -0.13
    ugu
    -0.13
    iche
    -0.13
    decorate
    -0.13
     Frankie
    -0.13
    POSITIVE LOGITS
     onCancelled
    0.15
    agento
    0.15
    otherwise
    0.14
    BorderStyle
    0.14
    è´¹
    0.14
     jinak
    0.14
    547
    0.14
    ancellor
    0.14
     elsewhere
    0.14
    DefaultValue
    0.13
    Act Density 0.185%

    No Known Activations