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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the abbreviation 'ph'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letters "ph" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -1.08
    ndra
    -0.76
    HCR
    -0.72
    ACTED
    -0.70
     merit
    -0.68
    eer
    -0.67
    ãĥĩ
    -0.67
    ãĥĥ
    -0.67
    nels
    -0.66
    eering
    -0.66
    POSITIVE LOGITS
    izoph
    1.14
    oenix
    1.10
    araoh
    0.99
    ysics
    0.96
    inx
    0.96
    yll
    0.95
    awei
    0.95
    osph
    0.94
     ph
    0.91
    antom
    0.91
    Act Density 0.007%

    No Known Activations