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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positioning or location

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating spatial positioning or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rug
    -0.71
    ories
    -0.70
    iple
    -0.69
    vari
    -0.69
    anship
    -0.68
    ivities
    -0.65
    ldom
    -0.65
    ague
    -0.63
    marine
    -0.63
    partial
    -0.63
    POSITIVE LOGITS
     cue
    1.11
     doorstep
    0.80
     front
    0.72
     heels
    0.70
     center
    0.64
     button
    0.63
    !:
    0.62
    oho
    0.61
    !?"
    0.61
     Bolt
    0.61
    Act Density 0.122%

    No Known Activations