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

    Neuronpedia

    INDEX
    Explanations

    unusual or digital content, likely with a focus on specific actions or desires within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ZO
    -0.15
    Bre
    -0.15
     Merc
    -0.15
    ãģķãģĦ
    -0.15
    andro
    -0.14
    .Logf
    -0.14
    oct
    -0.14
    оÑģÑĤей
    -0.14
     Bre
    -0.14
    Merc
    -0.14
    POSITIVE LOGITS
     Shadows
    0.22
     Investigation
    0.19
     Shadow
    0.18
     Persona
    0.17
     golden
    0.17
     Yuk
    0.17
     Golden
    0.16
     Velvet
    0.16
     y
    0.16
     murders
    0.16
    Act Density 0.007%

    No Known Activations