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

    Neuronpedia

    INDEX
    Explanations

    years and dates

    oai_token-act-pair · gpt-3.5-turbo

    instances of common introductory phrases or sentence starters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.78
    EStream
    -0.66
     guiActiveUnfocused
    -0.63
     respectively
    -0.61
    assad
    -0.61
    ospital
    -0.60
    agara
    -0.59
    ricane
    -0.58
    cellaneous
    -0.58
    itiz
    -0.58
    POSITIVE LOGITS
    oret
    0.65
     Bomber
    0.54
     Timeline
    0.51
    asm
    0.51
    sofar
    0.51
     Dating
    0.50
     Opinion
    0.50
    Especially
    0.50
     apologies
    0.49
     consequence
    0.48
    Act Density 0.809%

    No Known Activations