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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "on its own" appears

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "on its own."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hesda
    -0.72
    obar
    -0.72
    anchester
    -0.71
    ammy
    -0.70
    anwhile
    -0.68
    enegger
    -0.68
    assium
    -0.63
    phis
    -0.63
    ngth
    -0.62
    wy
    -0.62
    POSITIVE LOGITS
     accord
    0.78
     behalf
    0.78
    Cloud
    0.76
     island
    0.75
     footing
    0.74
     turf
    0.73
     islands
    0.72
     hands
    0.71
     backyard
    0.69
     board
    0.69
    Act Density 0.028%

    No Known Activations