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

    Neuronpedia

    INDEX
    Explanations

    names of people or entities along with a verb indicating action

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" and its variations indicating status or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiveness
    -0.68
    iates
    -0.61
    ear
    -0.59
    )).
    -0.58
    —"
    -0.57
    rouse
    -0.56
     latch
    -0.55
     entails
    -0.54
    role
    -0.54
    catch
    -0.53
    POSITIVE LOGITS
    senal
    0.95
     hereby
    0.79
     awarded
    0.75
     rumored
    0.74
     indeed
    0.70
     not
    0.67
    cussion
    0.67
     listed
    0.67
     NOT
    0.66
     also
    0.65
    Act Density 1.225%

    No Known Activations