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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collaborations and teamwork

    oai_token-act-pair · gpt-3.5-turbo

    references to opportunities and social invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Survivors
    -0.70
     offenders
    -0.70
     Pastebin
    -0.69
     commentators
    -0.68
     deletion
    -0.68
     Commentary
    -0.68
     Contains
    -0.64
     Percentage
    -0.64
     Miscellaneous
    -0.64
     Remain
    -0.63
    POSITIVE LOGITS
     intrigued
    1.11
     promptly
    0.96
     lured
    0.92
     soon
    0.91
     hooked
    0.91
     hatched
    0.88
     instantly
    0.88
     reluctantly
    0.86
     duly
    0.85
     ensued
    0.85
    Act Density 0.702%

    No Known Activations