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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating superlative or prominent qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampler
    -0.18
    _BOOL
    -0.16
    ût
    -0.16
    deaux
    -0.15
    rica
    -0.15
    _warn
    -0.15
    aign
    -0.15
    iaux
    -0.14
    .onDestroy
    -0.14
     reserve
    -0.13
    POSITIVE LOGITS
    illi
    0.15
    oho
    0.15
    integral
    0.15
    Pocket
    0.14
    è¿ŀ
    0.14
    among
    0.14
    Alive
    0.13
    ently
    0.13
     cose
    0.13
    seg
    0.13
    Act Density 0.078%

    No Known Activations