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

    Neuronpedia

    INDEX
    Explanations

    geometrical and positional relationships in mechanical or structural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .extern
    -0.16
    ispiel
    -0.14
    RowAt
    -0.14
    .slim
    -0.14
    HONE
    -0.14
    alto
    -0.14
    .à¸Ħ
    -0.14
    esty
    -0.14
    opolitan
    -0.13
    917
    -0.13
    POSITIVE LOGITS
     relative
    0.77
    relative
    0.69
     Relative
    0.65
    Relative
    0.57
     оÑĤноÑģ
    0.52
     wr
    0.52
    .relative
    0.52
     respecto
    0.50
    _relative
    0.49
    (relative
    0.49
    Act Density 0.221%

    No Known Activations