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

    Neuronpedia

    INDEX
    Explanations

    references to organized groups or committees focused on specific objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertino
    -0.15
    ĤŃ
    -0.14
     Relatives
    -0.14
    Fallback
    -0.14
    adÃŃ
    -0.13
    MMdd
    -0.13
    ayout
    -0.13
    enda
    -0.12
    Leaks
    -0.12
    Ngh
    -0.12
    POSITIVE LOGITS
     force
    0.98
    force
    0.88
     Force
    0.83
    -force
    0.80
    Force
    0.73
     FORCE
    0.71
     forces
    0.71
    _force
    0.70
    .force
    0.68
    forces
    0.63
    Act Density 0.036%

    No Known Activations