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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust and relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -0.95
    RenderAtEndOf
    -0.91
     الدولى
    -0.84
    Vidite
    -0.84
     Reſ
    -0.82
     TestBed
    -0.81
     ―――――
    -0.81
    expandindo
    -0.79
     Houſe
    -0.79
     Majefty
    -0.79
    POSITIVE LOGITS
     and
    0.52
     ex
    0.44
     Mag
    0.44
     him
    0.44
     former
    0.44
     us
    0.43
     D
    0.42
    +:+
    0.42
     now
    0.41
     filhos
    0.41
    Act Density 1.117%

    No Known Activations