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

    Neuronpedia

    INDEX
    Explanations

    complex sentences with technical and critical language

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to claims, opinions, or interpretations about a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.76
     thereafter
    -0.63
     Sudan
    -0.58
    ircraft
    -0.57
     Rehab
    -0.57
     refurb
    -0.56
     recalls
    -0.55
    ICLE
    -0.55
     Tourism
    -0.53
     doubtless
    -0.53
    POSITIVE LOGITS
    udic
    0.61
    Magikarp
    0.61
    eq
    0.60
    omething
    0.60
     negativity
    0.58
    ocr
    0.57
     innate
    0.57
    SI
    0.57
    hematically
    0.56
    ?",
    0.55
    Act Density 1.793%

    No Known Activations