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

    Neuronpedia

    INDEX
    Explanations

    links or references indicated by the symbol '.*' or similar symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of punctuation or special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chimera
    -0.82
     RTX
    -0.64
     Clever
    -0.62
     Honour
    -0.61
    rupted
    -0.61
     Emin
    -0.60
    elong
    -0.60
     Volt
    -0.59
     Dirty
    -0.58
    onnaissance
    -0.58
    POSITIVE LOGITS
    .*
    2.44
    .(
    2.34
    )(
    1.67
    .�
    1.66
    *.
    1.64
     (*
    1.50
    *,
    1.46
    :(
    1.45
    .#
    1.43
     (#
    1.37
    Act Density 0.042%

    No Known Activations