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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reasoning or justification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use the word "based" followed by various contexts or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.84
    Forge
    -0.83
    RL
    -0.76
    bats
    -0.70
    Cub
    -0.70
    vous
    -0.70
    associated
    -0.68
    ffect
    -0.66
    jah
    -0.65
    zon
    -0.64
    POSITIVE LOGITS
     behalf
    0.99
     sheer
    0.79
     principles
    0.73
     principle
    0.72
     hears
    0.72
     suspicion
    0.70
     demand
    0.69
     Demand
    0.69
     scraps
    0.68
     Sundays
    0.67
    Act Density 0.057%

    No Known Activations