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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional or contrasting concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪÛĮØ´
    -0.17
    adium
    -0.16
     rs
    -0.14
    achuset
    -0.14
    販
    -0.14
    erland
    -0.14
    sons
    -0.13
    amba
    -0.13
     entire
    -0.13
     vys
    -0.13
    POSITIVE LOGITS
    .opendaylight
    0.16
    mrt
    0.15
    yte
    0.15
    zza
    0.14
    esiz
    0.14
    PointerException
    0.14
    eldorf
    0.13
    eki
    0.13
    WARD
    0.13
    anz
    0.13
    Act Density 0.285%

    No Known Activations