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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unexpected outcomes and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate attempts or actions that lead to results or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mining
    -0.78
    ahead
    -0.75
     Donation
    -0.75
    matter
    -0.74
    holder
    -0.67
    processing
    -0.66
    kernel
    -0.65
    medium
    -0.65
    umption
    -0.65
    protection
    -0.65
    POSITIVE LOGITS
     discover
    1.21
     realise
    1.19
     realize
    1.16
     reapp
    1.03
     succumb
    1.01
     find
    0.98
     subsequently
    0.95
     awaken
    0.94
     stumble
    0.92
     later
    0.91
    Act Density 0.039%

    No Known Activations