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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating situations or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    418
    -0.15
    adi
    -0.15
    acies
    -0.14
     Zam
    -0.14
    ogs
    -0.14
    iceps
    -0.14
    alic
    -0.14
     Gin
    -0.13
    isser
    -0.13
     scale
    -0.13
    POSITIVE LOGITS
    olson
    0.16
     mpfr
    0.14
    .cx
    0.14
    deaux
    0.14
    orris
    0.14
    lero
    0.14
    isté
    0.14
    uppe
    0.14
     SCIP
    0.14
    .databinding
    0.13
    Act Density 0.163%

    No Known Activations