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

    Neuronpedia

    INDEX
    Explanations

    references to eating or the act of taking bites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GoogleMap
    -0.73
     Martens
    -0.67
     Kurtz
    -0.66
     mxArray
    -0.63
     Gymnas
    -0.63
    herjee
    -0.62
    heil
    -0.61
    avadoc
    -0.61
     monti
    -0.61
     Dolan
    -0.61
    POSITIVE LOGITS
     Bite
    0.99
     probes
    0.97
     Shy
    0.96
     bites
    0.94
     bite
    0.91
     shy
    0.91
     refra
    0.89
     hinting
    0.83
     probe
    0.82
     Probes
    0.82
    Act Density 0.143%

    No Known Activations