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

    Neuronpedia

    INDEX
    Explanations

    concepts related to existential and philosophical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morav
    -0.17
    oir
    -0.16
     ora
    -0.16
    quina
    -0.15
    amp
    -0.15
     Daniels
    -0.14
     Morr
    -0.14
    mor
    -0.14
     éľ
    -0.13
    Offsets
    -0.13
    POSITIVE LOGITS
     attachment
    0.22
     ego
    0.21
    attachment
    0.21
    ç´
    0.21
     attachments
    0.20
     Attachment
    0.20
     duk
    0.19
    Attachment
    0.19
     dual
    0.18
    Attachments
    0.17
    Act Density 0.142%

    No Known Activations