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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships involving people and their characteristics

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

    with group attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    -0.47
    namientos
    -0.38
    itself
    -0.36
     BEING
    -0.36
    guardo
    -0.34
     people
    -0.33
    спользова
    -0.32
    作为一个
    -0.31
    ity
    -0.31
     Itself
    -0.31
    POSITIVE LOGITS
     którzy
    0.73
    jsii
    0.69
     kteří
    0.67
     Normdatei
    0.66
     whom
    0.66
     disabilities
    0.66
     ktorí
    0.65
    IntoConstraints
    0.63
     who
    0.63
    ArgsConstructor
    0.61
    Act Density 0.078%

    No Known Activations