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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement or transfer

    oai_token-act-pair · gpt-3.5-turbo

    references to actions of moving or shifting subjects and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.70
     Breach
    -0.66
     Pact
    -0.64
    nces
    -0.64
    ottest
    -0.63
     Valid
    -0.63
    Miller
    -0.63
     Failure
    -0.62
    @#&
    -0.61
     pse
    -0.61
    POSITIVE LOGITS
     cursor
    1.11
     closer
    1.08
     needle
    0.95
     forward
    0.95
     toward
    0.93
    izont
    0.89
     hither
    0.89
     nearer
    0.87
     pend
    0.86
     forwards
    0.86
    Act Density 0.186%

    No Known Activations