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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical contact or proximity

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     redes
    -0.68
    yssey
    -0.67
    invoke
    -0.66
    never
    -0.66
    voice
    -0.65
    HCR
    -0.64
     succinct
    -0.64
     opting
    -0.64
    Month
    -0.62
    krit
    -0.61
    POSITIVE LOGITS
     objects
    1.02
     bushes
    1.01
     corpses
    0.96
     rocks
    0.94
     trees
    0.88
    objects
    0.88
     walls
    0.88
     stray
    0.85
     stones
    0.84
     garbage
    0.82
    Act Density 0.454%

    No Known Activations