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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a decline or deterioration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifice
    -0.19
    feit
    -0.17
    oso
    -0.16
    illary
    -0.15
    nis
    -0.15
    work
    -0.14
    ialized
    -0.14
    MOOTH
    -0.14
    rax
    -0.14
    bian
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.18
    azar
    0.18
    acies
    0.16
    ments
    0.16
    acons
    0.15
    urse
    0.15
    ActionCode
    0.15
    utor
    0.15
    ryptography
    0.14
    /rest
    0.14
    Act Density 0.025%

    No Known Activations