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

    Neuronpedia

    INDEX
    Explanations

    words related to specific names and locations, particularly those with the pattern "Wol", "Rab", "Wilde", "Wer", and "Wald"

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those related to individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irt
    -0.69
    ead
    -0.67
     increment
    -0.66
     iT
    -0.65
     spect
    -0.64
    teen
    -0.63
     joints
    -0.63
    Space
    -0.63
     mortar
    -0.62
    thood
    -0.60
    POSITIVE LOGITS
     Wol
    4.01
     Rab
    1.45
     Wilde
    1.42
     Wer
    1.26
     Kru
    1.10
     Kra
    1.05
     Werner
    1.05
     Schro
    1.02
     Naw
    1.01
     Wald
    1.01
    Act Density 0.030%

    No Known Activations