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

    Neuronpedia

    INDEX
    Explanations

    locations or places within a setting

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     bitters
    -0.60
     epit
    -0.56
     fundament
    -0.56
     ensued
    -0.56
     param
    -0.55
    etically
    -0.53
    rane
    -0.53
     follows
    -0.52
     Chaser
    -0.52
    },
    -0.52
    POSITIVE LOGITS
     waiting
    0.86
     lookout
    0.84
     preparing
    0.78
     awaiting
    0.78
     somewhere
    0.77
     ready
    0.75
     photograp
    0.75
     discussing
    0.74
     watching
    0.72
     listening
    0.71
    Act Density 0.442%

    No Known Activations