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

    Neuronpedia

    INDEX
    Explanations

    negative references or sentiments towards familial relationships

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

    brother-in-law / daughter-in-law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.40
    หวัด
    -0.36
    Competition
    -0.34
    Occupation
    -0.34
    The
    -0.34
    Portail
    -0.33
    HideFlags
    -0.32
     ceci
    -0.32
     explotación
    -0.31
    abestanden
    -0.31
    POSITIVE LOGITS
     ſch
    0.71
     ſta
    0.69
     ſind
    0.66
     Conſ
    0.66
    ſelves
    0.63
     pleaſure
    0.63
     Inſ
    0.63
     ſte
    0.62
     purpoſe
    0.62
    edipus
    0.61
    Act Density 0.010%

    No Known Activations