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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate comparisons or likeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dafx
    -0.56
     faptul
    -0.53
     كومونز
    -0.53
     asupra
    -0.47
     oamen
    -0.47
     huéspedes
    -0.46
     oamenii
    -0.45
    vraag
    -0.45
     Signalez
    -0.44
    correre
    -0.44
    POSITIVE LOGITS
     appear
    0.54
     Looks
    0.53
    Looks
    0.52
     Meksiku
    0.49
     appearance
    0.47
     appears
    0.47
     looks
    0.47
     resemble
    0.45
     выгля
    0.44
     Appears
    0.44
    Act Density 0.139%

    No Known Activations