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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media

    oai_token-act-pair · gpt-3.5-turbo

    references to social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.98
    xual
    -0.83
    ilts
    -0.77
     Cursed
    -0.74
    shall
    -0.71
    atche
    -0.70
     Centauri
    -0.69
    ered
    -0.68
    ARDS
    -0.66
    ras
    -0.66
    POSITIVE LOGITS
     networking
    0.96
     networks
    0.94
    izing
    0.90
    ized
    0.83
     gatherings
    0.82
    istic
    0.80
     norms
    0.78
    izers
    0.78
    ization
    0.78
     cues
    0.76
    Act Density 0.026%

    No Known Activations