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

    Neuronpedia

    INDEX
    Explanations

    recurring themes and patterns in experiences and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unlike
    -0.18
    zar
    -0.16
    enaire
    -0.16
    orre
    -0.15
    Unlike
    -0.15
     optionally
    -0.15
    erate
    -0.15
     Unlike
    -0.15
    hin
    -0.14
    atel
    -0.14
    POSITIVE LOGITS
     same
    0.62
    same
    0.58
    缸åIJĮ
    0.54
    Same
    0.52
     Same
    0.52
     identical
    0.52
     SAME
    0.47
    _same
    0.45
     similar
    0.44
    åIJĮ
    0.44
    Act Density 0.056%

    No Known Activations