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

    Neuronpedia

    INDEX
    Explanations

    the word "unless" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erken
    -0.16
    udic
    -0.15
    OME
    -0.15
    ãģ©
    -0.14
    jo
    -0.14
    hsi
    -0.14
    SCO
    -0.14
    aus
    -0.14
    anst
    -0.14
    ercul
    -0.14
    POSITIVE LOGITS
    /un
    0.36
     otherwise
    0.29
     they
    0.22
     there
    0.20
     OTHERWISE
    0.19
     we
    0.18
     perhaps
    0.18
     Otherwise
    0.18
     it
    0.17
    otherwise
    0.17
    Act Density 0.009%

    No Known Activations