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

    Neuronpedia

    INDEX
    Explanations

    transition words indicating cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    the word "thus" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ten
    -0.63
    isable
    -0.60
     Kl
    -0.60
    igger
    -0.59
    UGH
    -0.58
    Õ
    -0.57
    kick
    -0.57
     killer
    -0.55
    umble
    -0.55
    ForgeModLoader
    -0.54
    POSITIVE LOGITS
    forth
    1.10
    forward
    0.94
    tainment
    0.84
     guiActiveUn
    0.83
    bered
    0.79
     convol
    0.77
    apy
    0.77
    fter
    0.75
    mask
    0.75
    bda
    0.75
    Act Density 0.014%

    No Known Activations