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

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbial forms that describe emotional states or attitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ==
    -0.16
     crow
    -0.15
    otp
    -0.15
     –
    -0.15
    леÑĩ
    -0.14
    hl
    -0.13
    zew
    -0.13
     mil
    -0.13
    enan
    -0.13
    ersions
    -0.12
    POSITIVE LOGITS
    iew
    0.15
    !
    0.14
    ovit
    0.14
    rak
    0.14
    806
    0.14
    !")
    0.14
     amac
    0.14
    ?↵↵↵
    0.14
    !]
    0.13
    SmartPointer
    0.13
    Act Density 0.000%

    No Known Activations