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

    Neuronpedia

    INDEX
    Explanations

    structures and organizational elements within a text, such as lists or sections

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological species and environmental conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bankrupt
    -0.78
     panicked
    -0.76
     deserted
    -0.76
    apsed
    -0.74
     stunned
    -0.70
     raged
    -0.70
     shocked
    -0.69
     raging
    -0.66
    awed
    -0.66
     disgr
    -0.65
    POSITIVE LOGITS
     preferably
    1.48
     ideally
    1.27
     Ideally
    1.22
     hopefully
    1.21
    Alternatively
    1.03
     optionally
    1.01
     Alternatively
    0.98
    Otherwise
    0.98
     incorporate
    0.97
     possibly
    0.95
    Act Density 0.908%

    No Known Activations