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

    Neuronpedia

    INDEX
    Explanations

    statements focusing on the consequences of actions and social behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antan
    -0.15
    elman
    -0.15
    rico
    -0.15
    kers
    -0.15
    ajaran
    -0.14
    aiser
    -0.14
    ıt
    -0.14
    iju
    -0.14
    uxt
    -0.14
    loys
    -0.14
    POSITIVE LOGITS
    /null
    0.19
     itself
    0.18
    inta
    0.17
    ulla
    0.16
     dess
    0.15
    lings
    0.15
     thereof
    0.14
     ÑģобоÑİ
    0.14
    ska
    0.14
    INLINE
    0.14
    Act Density 0.304%

    No Known Activations