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

    Neuronpedia

    INDEX
    Explanations

    interjections and exclamations used in casual language

    oai_token-act-pair · gpt-3.5-turbo

    commas in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.83
    escription
    -0.76
    %:
    -0.69
    hig
    -0.69
    :[
    -0.69
    icipated
    -0.69
    iband
    -0.68
    gat
    -0.67
    atform
    -0.66
    mop
    -0.66
    POSITIVE LOGITS
     anyway
    1.36
     alas
    1.31
     incidentally
    1.27
     huh
    1.17
     eh
    1.16
     yeah
    1.12
     yes
    1.10
     anyways
    1.08
     admittedly
    1.04
     thankfully
    0.96
    Act Density 0.298%

    No Known Activations