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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to combining or configuring different elements or components

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "combo" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aniel
    -0.74
    mberg
    -0.73
    unc
    -0.73
    pher
    -0.70
    igr
    -0.69
    oral
    -0.69
    ady
    -0.68
     Abraham
    -0.65
     Wage
    -0.65
    pir
    -0.64
    POSITIVE LOGITS
     Breaker
    0.92
     boxes
    0.76
     combo
    0.75
    halla
    0.72
     breaker
    0.71
     Combo
    0.70
     combos
    0.69
     mash
    0.69
     bundle
    0.69
    iques
    0.68
    Act Density 0.007%

    No Known Activations