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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing effects and their relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    identifying an effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    олові
    -0.46
    ̈́
    -0.44
     AssemblyCompany
    -0.44
     eletrônico
    -0.43
    nthetic
    -0.41
     mijne
    -0.41
    amante
    -0.40
    lebo
    -0.40
     Perusahaan
    -0.39
     moletom
    -0.39
    POSITIVE LOGITS
     effect
    1.84
    effect
    1.82
     Effect
    1.72
    Effect
    1.72
     effects
    1.71
     Effects
    1.64
    Effects
    1.62
    effects
    1.60
     EFFECT
    1.48
    effetto
    1.46
    Act Density 0.095%

    No Known Activations