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

    Neuronpedia

    INDEX
    Explanations

    references to jukeboxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens starting with "ju" followed by specific letters

    np_acts-logits-general · gemini-2.0-flash

    ju followed by specific endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.53
     con
    -0.51
    SourceChecksum
    -0.48
    zkod
    -0.44
     EClass
    -0.44
    ništ
    -0.43
     (
    -0.43
     b
    -0.42
     l
    -0.42
     [
    -0.41
    POSITIVE LOGITS
    enumi
    1.04
    twimg
    0.85
     Theſe
    0.82
     EconPapers
    0.80
    Portale
    0.79
     ProtoMessage
    0.78
     Anſ
    0.76
     Monfieur
    0.76
     useAppContext
    0.73
     Juf
    0.73
    Act Density 0.079%

    No Known Activations