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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations or hypothetical scenarios

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.66
    Contours
    -0.54
    enderror
    -0.49
    الدراسه
    -0.48
     justicia
    -0.45
    Зноскі
    -0.45
    يميديا
    -0.44
    rungsseite
    -0.44
    AMPTON
    -0.42
     fjor
    -0.42
    POSITIVE LOGITS
     myſelf
    0.77
     ſch
    0.75
     Diſ
    0.75
     Perſ
    0.73
     Monfieur
    0.71
     ISNI
    0.70
     ſtre
    0.69
     Majefty
    0.69
     Inſ
    0.68
     Theſe
    0.68
    Act Density 0.036%

    No Known Activations