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

    phrases describing actions or results related to "making out" and other similar activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.71
    hovah
    -0.70
     overfl
    -0.68
     exting
    -0.67
    phrine
    -0.63
     horizont
    -0.61
    SPONSORED
    -0.59
     overflow
    -0.59
    rect
    -0.59
    Constructed
    -0.59
    POSITIVE LOGITS
     noises
    0.76
    ota
    0.70
    sense
    0.70
    nell
    0.69
    CAST
    0.69
    ouse
    0.68
     mole
    0.66
    ilan
    0.64
     Lei
    0.63
    Wan
    0.63
    Act Density 0.108%

    No Known Activations