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

    Neuronpedia

    INDEX
    Explanations

    a verb followed by a preposition

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.84
    requires
    -0.75
     Compass
    -0.71
     Appears
    -0.70
    currently
    -0.69
    lies
    -0.68
     presently
    -0.65
    ready
    -0.64
    soever
    -0.64
    plates
    -0.64
    POSITIVE LOGITS
     postpone
    0.99
     injure
    0.98
     violate
    0.94
     evacuate
    0.94
     eliminate
    0.92
     overthrow
    0.92
     submit
    0.92
     reassure
    0.90
     remove
    0.90
     meet
    0.90
    Act Density 0.327%

    No Known Activations