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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    references to sadness and negative emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouver
    -0.77
    entials
    -0.73
    authorized
    -0.71
    RAFT
    -0.67
     FANT
    -0.66
    Testing
    -0.64
    gat
    -0.63
    gemony
    -0.63
    VERTISEMENT
    -0.63
     vetted
    -0.63
    POSITIVE LOGITS
    der
    1.33
    omas
    1.30
    istically
    1.09
    istic
    1.08
    die
    0.91
    stal
    0.84
     Nadu
    0.83
    Sad
    0.82
    mouth
    0.80
    biz
    0.79
    Act Density 0.032%

    No Known Activations