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

    Neuronpedia

    INDEX
    Explanations

    phrases related to action of picking something up

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the action of lifting or raising something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.64
    ãĥĥãĤ¯
    -0.61
     CLR
    -0.59
     Annotations
    -0.57
    ories
    -0.56
    iasm
    -0.56
     Patron
    -0.56
    anton
    -0.55
     background
    -0.55
     Scor
    -0.54
    POSITIVE LOGITS
     cheaply
    0.92
    handedly
    0.77
     altogether
    0.76
     somehow
    0.76
     offensively
    0.75
     aloud
    0.74
     again
    0.74
     territ
    0.73
    handed
    0.72
     administr
    0.71
    Act Density 0.147%

    No Known Activations