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

    Neuronpedia

    INDEX
    Explanations

    references to people and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cross
    -0.41
     Ancient
    -0.40
    mstyle
    -0.39
     Solidar
    -0.39
     Instant
    -0.39
    Trọng
    -0.38
     Historic
    -0.38
    Historic
    -0.37
    indrical
    -0.37
     the
    -0.37
    POSITIVE LOGITS
     그녀
    0.85
    them
    0.82
     them
    0.79
    herself
    0.76
     juos
    0.76
     him
    0.76
     she
    0.76
    She
    0.75
     THEM
    0.75
    Them
    0.75
    Act Density 0.187%

    No Known Activations