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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and pleas for help

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

    Follows first-person pronouns

    np_acts-logits-general · gemini-2.0-flash

    words before question phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.51
    SBATCH
    -0.51
     conclusão
    -0.51
    PointerException
    -0.47
    省市镇
    -0.46
    Хьажоргаш
    -0.45
    VIAF
    -0.44
     instituição
    -0.43
    tratamiento
    -0.43
    volvement
    -0.43
    POSITIVE LOGITS
    baomidou
    0.42
    évaluateur
    0.41
    ✨:
    0.39
     don
    0.38
     BoxFit
    0.36
     Christian
    0.36
     esterni
    0.35
    లాలు
    0.35
    nodoc
    0.35
    doria
    0.35
    Act Density 0.303%

    No Known Activations