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

    Neuronpedia

    INDEX
    Explanations

    phrases related to imagining scenarios or events

    oai_token-act-pair · gpt-3.5-turbo

    conjectures or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isphere
    -0.60
    Kings
    -0.55
     canopy
    -0.54
    stuff
    -0.52
     Cologne
    -0.52
     Euph
    -0.52
    Spoiler
    -0.52
    oster
    -0.52
     Gran
    -0.52
    Gab
    -0.51
    POSITIVE LOGITS
    govtrack
    0.61
    ļé
    0.59
    ultane
    0.57
     alternatively
    0.56
     secondly
    0.56
    erest
    0.55
    anwhile
    0.55
    vertisement
    0.54
    any
    0.54
     lesbians
    0.53
    Act Density 1.079%

    No Known Activations