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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific people or characters collaborating together

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of past tense verbs and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiz
    -0.78
    rina
    -0.75
    afety
    -0.72
    stem
    -0.67
    uria
    -0.66
    ento
    -0.65
    teness
    -0.62
     Machina
    -0.60
    Downloadha
    -0.60
    earcher
    -0.59
    POSITIVE LOGITS
     respectively
    1.93
     alike
    1.27
     together
    1.14
     jointly
    1.09
    together
    1.06
     respective
    1.02
     Together
    0.92
     collectively
    0.84
    Together
    0.84
    OTH
    0.83
    Act Density 0.614%

    No Known Activations