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

    Neuronpedia

    INDEX
    Explanations

    phrases related to responsibility and progress in various contexts

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

    viewpoint terms perspective viewpoint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.43
     cesse
    -0.40
    rrggbb
    -0.40
     tetrachloride
    -0.39
     contacter
    -0.39
     Passage
    -0.39
     AttributeSet
    -0.38
     trained
    -0.38
    accompanied
    -0.36
     tongue
    -0.36
    POSITIVE LOGITS
    ofern
    0.56
    Technically
    0.55
     autorytatywna
    0.55
    发表于
    0.52
    setof
    0.51
    FWIW
    0.51
    的には
    0.48
    makeConstraints
    0.47
    urally
    0.46
    Essentially
    0.46
    Act Density 0.034%

    No Known Activations